Prediction system for simulating the effects of a real-world event

Abstract

A prediction system for simulating effects of a real-world event can be used for autonomous driving. In operation, the system receives input data regarding a complex system (e.g., roadways) and various real-world events. A full-scale network is constructed of the complex system, such that nodes represent road intersections and edges between nodes represent road segments linking the road intersections. The network is reduced is scaled down to generate a multi-layer model of the complex system. Each layer in the model is simulated to identify equilibrium flows, with the model thereafter destabilized by applying stimuli to reflect the real-world event. An autonomous vehicle can then be caused to chart and traverse a road path based on road segments and intersections that are least affected by the real-world event.

What is claimed is: 
     
       1. A prediction system for simulating effects of a real-world event, the system comprising:
 one or more processors and a memory, the memory being a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions, the one or more processors perform operations of:
 receiving input data regarding a complex system, the input data having at least a first parameter, a second parameter, and stimuli specifications; 
 constructing a full-scale network of the complex system based on the first parameter, such that nodes represent intersecting similarities between components in the first parameter and edges linking the nodes represent distances between nodes; 
 generating a reduced network by merging nodes whose locations are within a predefined shape; 
 scaling-down the reduced network by clustering the nodes based on location and merging all nodes in a same cluster; 
 generating a multi-layer model of the complex system through setting node features by associating the second parameter to each node; 
 simulating each layer in the multi-layer model to identify equilibrium flows of the multi-layer model; 
 applying stimuli to the multi-layer model to destabilize the multi-layer model, the stimuli reflecting at least one real-world event as associated with the complex system; and 
 generating a list of stimuli reflecting a ranking of affected edges between nodes and associated changes in flow in response to each applied stimuli. 
 
 
     
     
       2. The prediction system as set forth in  claim 1 , further comprising an operation of causing a device to implement an action based on occurrence of the real-world event. 
     
     
       3. The prediction system as set forth in  claim 2 , wherein the action is based on the list of stimuli to cause the device to operate according to edges least affected in response to the stimuli associated with the real-world event. 
     
     
       4. The prediction system as set forth in  claim 3 , wherein the complex system includes roadways within a city and the first parameter includes road data and the second parameter includes population data. 
     
     
       5. The prediction system as set forth in  claim 4 , where nodes in the full-scale network represent road intersections and edges between nodes represent road segments linking the road intersections. 
     
     
       6. The prediction system as set forth in  claim 5 , wherein causing a device to implement an action based on occurrence of the real-world event includes causing an autonomous vehicle to chart and traverse a road path based on road segments and intersections that are least affected by the real-world event. 
     
     
       7. The prediction system as set forth in  claim 2 , where nodes in the full-scale network represent road intersections and edges between nodes represent road segments linking the road intersections. 
     
     
       8. The prediction system as set forth in  claim 7 , wherein causing a device to implement an action based on occurrence of the real-world event includes causing an autonomous vehicle to chart and traverse a road path based on road segments and intersections that are least affected by the real-world event. 
     
     
       9. The prediction system as set forth in  claim 1 , wherein the complex system includes roadways within a city and the first parameter includes road data and the second parameter includes population data. 
     
     
       10. A computer program product on a non-transitory computer-readable medium for simulating effects of a real-world event, the computer program product comprising:
 a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions by one or more processors, the one or more processors perform operations of:
 receiving input data regarding a complex system, the input data having at least a first parameter, a second parameter, and stimuli specifications; 
 constructing a full-scale network of the complex system based on the first parameter, such that nodes represent intersecting similarities between components in the first parameter and edges linking the nodes represent distances between nodes; 
 generating a reduced network by merging nodes whose locations are within a predefined shape; 
 scaling-down the reduced network by clustering the nodes based on location and merging all nodes in a same cluster; 
 generating a multi-layer model of the complex system through setting node features by associating the second parameter to each node; 
 simulating each layer in the multi-layer model to identify equilibrium flows of the multi-layer model; 
 applying stimuli to the multi-layer model to destabilize the multi-layer model, the stimuli reflecting at least one real-world event as associated with the complex system; and 
 generating a list of stimuli reflecting a ranking of effected edges between nodes and associated changes in flow in response to each applied stimuli. 
 
 
     
     
       11. The computer program product as set forth in  claim 10 , further comprising instructions for causing a device to implement an action based on occurrence of the real-world event. 
     
     
       12. The computer program product as set forth in  claim 11 , wherein the action is based on the list of stimuli to cause the device to operate according to edges least affected in response to the stimuli associated with the real-world event. 
     
     
       13. The computer program product as set forth in  claim 12 , wherein the complex system includes roadways within a city and the first parameter includes road data and the second parameter includes population data. 
     
     
       14. The computer program product as set forth in  claim 13 , where nodes in the full-scale network represent road intersections and edges between nodes represent road segments linking the road intersections. 
     
     
       15. The computer program product as set forth in  claim 14 , wherein causing a device to implement an action based on occurrence of the real-world event includes causing an autonomous vehicle to chart and traverse a road path based on road segments and intersections that are least affected by the real-world event. 
     
     
       16. The computer program product as set forth in  claim 11 , where nodes in the full-scale network represent road intersections and edges between nodes represent road segments linking the road intersections. 
     
     
       17. The computer program product as set forth in  claim 16 , wherein causing a device to implement an action based on occurrence of the real-world event includes causing an autonomous vehicle to chart and traverse a road path based on road segments and intersections that are least affected by the real-world event. 
     
     
       18. The computer program product as set forth in  claim 10 , wherein the complex system includes roadways within a city and the first parameter includes road data and the second parameter includes population data. 
     
     
       19. A computer implemented method for predicting effects of a real-world event, the method comprising an act of:
 causing one or more processers to execute instructions encoded on a non-transitory computer-readable medium, such that upon execution, the one or more processors perform operations of:
 receiving input data regarding a complex system, the input data having at least a first parameter, a second parameter, and stimuli specifications; 
 constructing a full-scale network of the complex system based on the first parameter, such that nodes represent intersecting similarities between components in the first parameter and edges linking the nodes represent distances between nodes; 
 generating a reduced network by merging nodes whose locations are within a predefined shape; 
 scaling-down the reduced network by clustering the nodes based on location and merging all nodes in a same cluster; 
 generating a multi-layer model of the complex system through setting node features by associating the second parameter to each node; 
 simulating each layer in the multi-layer model to identify equilibrium flows of the multi-layer model; 
 applying stimuli to the multi-layer model to destabilize the multi-layer model, the stimuli reflecting at least one real-world event as associated with the complex system; and 
 generating a list of stimuli reflecting a ranking of effected edges between nodes and associated changes in flow in response to each applied stimuli. 
 
 
     
     
       20. The method as set forth in  claim 19 , further comprising an operation of causing a device to implement an action based on occurrence of the real-world event. 
     
     
       21. The method as set forth in  claim 20 , wherein the action is based on the list of stimuli to cause the device to operate according to edges least affected in response to the stimuli associated with the real-world event. 
     
     
       22. The method as set forth in  claim 21 , wherein the complex system includes roadways within a city and the first parameter includes road data and the second parameter includes population data. 
     
     
       23. The method as set forth in  claim 22 , where nodes in the full-scale network represent road intersections and edges between nodes represent road segments linking the road intersections. 
     
     
       24. The method as set forth in  claim 23 , wherein causing a device to implement an action based on occurrence of the real-world event includes causing an autonomous vehicle to chart and traverse a road path based on road segments and intersections that are least affected by the real-world event. 
     
     
       25. The method as set forth in  claim 20 , where nodes in the full-scale network represent road intersections and edges between nodes represent road segments linking the road intersections. 
     
     
       26. The method as set forth in  claim 25 , wherein causing a device to implement an action based on occurrence of the real-world event includes causing an autonomous vehicle to chart and traverse a road path based on road segments and intersections that are least affected by the real-world event. 
     
     
       27. The method as set forth in  claim 19 , wherein the complex system includes roadways within a city and the first parameter includes road data and the second parameter includes population data.